InternVQA: Advancing Compressed Video Quality Assessment with Distilling Large Foundation Model
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913708203048960 |
|---|---|
| author | Guan, Fengbin Yu, Zihao Lu, Yiting Li, Xin Chen, Zhibo |
| author_facet | Guan, Fengbin Yu, Zihao Lu, Yiting Li, Xin Chen, Zhibo |
| contents | Video quality assessment tasks rely heavily on the rich features required for video understanding, such as semantic information, texture, and temporal motion. The existing video foundational model, InternVideo2, has demonstrated strong potential in video understanding tasks due to its large parameter size and large-scale multimodal data pertaining. Building on this, we explored the transferability of InternVideo2 to video quality assessment under compression scenarios. To design a lightweight model suitable for this task, we proposed a distillation method to equip the smaller model with rich compression quality priors. Additionally, we examined the performance of different backbones during the distillation process. The results showed that, compared to other methods, our lightweight model distilled from InternVideo2 achieved excellent performance in compression video quality assessment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_19026 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | InternVQA: Advancing Compressed Video Quality Assessment with Distilling Large Foundation Model Guan, Fengbin Yu, Zihao Lu, Yiting Li, Xin Chen, Zhibo Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Video quality assessment tasks rely heavily on the rich features required for video understanding, such as semantic information, texture, and temporal motion. The existing video foundational model, InternVideo2, has demonstrated strong potential in video understanding tasks due to its large parameter size and large-scale multimodal data pertaining. Building on this, we explored the transferability of InternVideo2 to video quality assessment under compression scenarios. To design a lightweight model suitable for this task, we proposed a distillation method to equip the smaller model with rich compression quality priors. Additionally, we examined the performance of different backbones during the distillation process. The results showed that, compared to other methods, our lightweight model distilled from InternVideo2 achieved excellent performance in compression video quality assessment. |
| title | InternVQA: Advancing Compressed Video Quality Assessment with Distilling Large Foundation Model |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.19026 |